category focus

LLM & AI

Large Language Models and AI agents.

4725 skillsall categories
sorting
stars
current ordering strategy
query
all entries
refine the visible subset
llm-ai
1

resource-exhaustion-dos-ai-generated-code

Understand resource exhaustion and denial of service vulnerabilities in AI code including unbounded loops, missing rate limits, and uncontrolled resource consumption. Use this skill when you need to learn about DoS vulnerabilities in AI code, understand resource limits, recognize unbounded operations, or prevent resource exhaustion. Triggers include "resource exhaustion", "DoS vulnerabilities", "denial of service", "unbounded resources", "API cost protection", "memory exhaustion", "uncontrolled consumption", "rate limiting DoS".

harperaa
harperaa
data-ai
open
llm-ai
1

rag-systems

Retrieval-Augmented Generation - chunking strategies, embedding, vector search, hybrid retrieval, reranking, query transformation. Use when building RAG pipelines, knowledge bases, or context-augmented applications.

doanchienthangdev
doanchienthangdev
data-ai
open
llm-ai
1

mcp-development

Guide for creating MCP (Model Context Protocol) servers that enable LLMs to interact with external services. Use when building MCP servers, integrating external APIs, implementing tool servers, or creating agent capabilities. Covers TypeScript/Python patterns, tool design, and evaluation creation.

5dlabs
5dlabs
data-ai
open
llm-ai
1

search

단순 검색 - Haiku 모델로 빠르고 저렴하게

soundbluemusic
soundbluemusic
data-ai
open
llm-ai
1

skill-creator

建立有效技能的指南。當使用者想要建立新技能(或更新現有技能)以透過專業知識、工作流程或工具整合來擴展 Claude 的能力時,應使用此技能。

ammosu
ammosu
data-ai
open
llm-ai
1

ai-agent-basics

Master AI agent fundamentals - architectures, ReAct patterns, cognitive loops, and autonomous system design

pluginagentmarketplace
pluginagentmarketplace
data-ai
open
llm-ai
1

template-skill

Template for creating Claude Code skills. Use this as a starting point when building new skills for code formatting, testing, documentation generation, or other specialized workflows. Include both functionality and usage triggers in descriptions.

jwplatta
jwplatta
data-ai
open
llm-ai
1

using-superpowers

DEPRECATED - Merged into work-command-center as Phase 0. Use work-command-center instead.

mbcoalson
mbcoalson
data-ai
open
llm-aimarketplace
1

skill-creator

Use when creating new skills or editing existing skills - applies prompt engineering principles to write clear, goal-focused process documentation that trusts LLM intelligence

Krosebrook
Krosebrook
data-ai
open
llm-ai
1

research

Web research skill for augmenting agent context with current information. Used when outdated information could lead to broken implementations or wasted effort.

TechNickAI
TechNickAI
data-ai
open
llm-ai
1

skill-creator-enhanced

Creates production-grade, reusable skills that extend Claude's capabilities. This skill should be used when users want to create a new skill, improve an existing skill, or build domain-specific intelligence. Gathers context from codebase, conversation, and authentic sources before creating adaptable skills.

suhaibshaikh03
suhaibshaikh03
data-ai
open
llm-ai
1

mcp-architecture-expert

Design and implement Model Context Protocol servers for standardized AI-to-data integration with resources, tools, prompts, and security best practices

frankxai
frankxai
data-ai
open
llm-ai
1

prompt-lookup

Activates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat. Use for discovering, retrieving, and improving prompts.

pplmx
pplmx
data-ai
open
llm-ai
1

sub-agents

Create and configure Claude Code sub-agents with custom prompts, tools, and models

namesreallyblank
namesreallyblank
data-ai
open
llm-ai
1

openmemory

Persistent long-term agent memory for storing and querying past work, patterns, and learnings.

5dlabs
5dlabs
data-ai
open
llm-ai
1

using-superpowers

Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions

aRustyDev
aRustyDev
data-ai
open
llm-ai
1

layer-06-api

Expert knowledge for API Layer modeling in Documentation Robotics

tinkermonkey
tinkermonkey
data-ai
open
llm-ai
1

streamlit

When working with Streamlit web apps, data dashboards, ML/AI app UIs, interactive Python visualizations, or building data science applications with Python

sverzijl
sverzijl
data-ai
open
llm-ai
1

using-crispyclaude

Use when starting any conversation - establishes mandatory workflows for finding and using skills, including using Skill tool before announcing usage, following brainstorming before coding, and creating TodoWrite todos for checklists

seanGSISG
seanGSISG
data-ai
open
llm-ai
1

mcp-server-generator

Expert guidance for creating, configuring, and deploying Model Context Protocol (MCP) servers. Use when building custom MCP servers, integrating external APIs, or extending Claude with new capabilities.

Krosebrook
Krosebrook
data-ai
open
llm-ai
1

evaluation

Agent evaluation methods including LLM-as-judge, rubrics, and quality gates.

5dlabs
5dlabs
data-ai
open
llm-ai
1

googlemaps

Gemini Google Maps Grounding - Location-aware AI responses

Who-Visions
Who-Visions
data-ai
open
llm-ai
1

mcp-daemon-isolation

Context isolation for query-type MCP tools (LSP, search, database) via external CLI. Use when MCP query results consume too many context tokens.

chkim-su
chkim-su
data-ai
open
Previous
Page 136 / 197
Next